A Variance-Preserving Interpolation Approach for Diffusion Models With Applications to Single Channel Speech Enhancement and Recognition-Reference-Cited by-同舟云学术

登录注册会员服务联系我们

A Variance-Preserving Interpolation Approach for Diffusion Models With Applications to Single Channel Speech Enhancement and Recognition

Published:2024 Issue: Volume:32 Page:3025-3038
ISSN:2329-9290
Container-title:IEEE/ACM Transactions on Audio, Speech, and Language Processing
language:
Short-container-title:IEEE/ACM Trans. Audio Speech Lang. Process.

Author:

Guo Zilu¹^ORCID,Wang Qing¹^ORCID,Du Jun¹^ORCID,Pan Jia²,Liu Qing-Feng¹,Lee Chin-Hui³^ORCID

Affiliation:

1. National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China

2. iFLYTEK Research, Hefei, China

3. School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA

Funder

National Natural Science Foundation of China

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Link

http://xplorestaging.ieee.org/ielx8/6570655/10304349/10547426.pdf?arnumber=10547426

Reference61 articles.

1. New insights into the noise reduction Wiener filter

2. An analysis of environment, microphone and data simulation mismatches in robust speech recognition

3. Knowledge Distillation for Improved Accuracy in Spoken Question Answering

4. Self-supervised Contrastive Cross-Modality Representation Learning for Spoken Question Answering

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线，采集、加工和组织学术论文而形成的新型学术文献查询和分析系统，可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容，当前同舟云学术共收录了国内外主流学术期刊6万余种，收集的期刊论文及会议论文总量共计约1.5亿篇，并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询！咨询电话：010-8811{复制后删除}0370

www.globalauthorid.com

TOP